AIME: AI System Optimization via Multiple LLM Evaluators
Keywords: AI System Optimization, Agentic AI, Large Language Models, LLM-based Evaluation
TL;DR: Multiple LLM-based evaluators improves AI system optimization
Abstract: Text-based AI system optimization typically involves a feedback loop scheme where a \textit{single} LLM generates an evaluation in natural language of the current output to improve the next iteration's output. However, in this work, we empirically demonstrate that for a practical and complex task (code generation) with multiple criteria to evaluate, utilizing only one LLM evaluator tends to let errors in generated code go undetected, thus leading to incorrect evaluations and ultimately suboptimal test case performance. Motivated by this failure case, we assume there exists an optimal evaluation policy that samples an evaluation between response and ground truth. We then theoretically prove that a linear combination of multiple evaluators can approximate this optimal policy. From this insight, we propose AI system optimization via Multiple LLM Evaluators (AIME). AIME is an evaluation protocol that utilizes multiple LLMs that each independently generate an evaluation on separate criteria and then combine them via concatenation. We provide an extensive empirical study showing AIME outperforming baseline methods in code generation tasks, with up to 62\% higher error detection rate and up to 16\% higher success rate than a single LLM evaluation protocol on LeetCodeHard and HumanEval datasets. We also show that the selection of the number of evaluators and which criteria to utilize is non-trivial as it can impact pact success rate by up to 12\%.
Primary Area: foundation or frontier models, including LLMs
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 10727
Loading